Abnormality Segmentation and Classification of Multi-class Brain Tumor in MR Images Using Fuzzy Logic-Based Hybrid Kernel SVM

Abstract

Image classification is one of the typical computational applications widely used in the medical field, especially for abnormality detection in magnetic resonance (MR) brain images. Medical image classification is a pattern recognition technique in which different images are categorized into several groups based on some similarity measures. One of the significant applications is the tumor type identification in abnormal MR brain images. The proposed multi-class brain tumor classification system comprises feature extraction and classification. In feature extraction, the attributes of the co-occurrence matrix and the histogram are represented within the feature vector. In this work, the advantage of both co-occurrence matrix and histogram to extract the texture feature from every segment is used for better classification. In classification, the fuzzy logic-based hybrid kernel is designed and applied to train the support vector machine for automatic classification of four different types of brain tumors such as Meningioma, Glioma, Astrocytoma, and Metastases. Based on the experimental results, the proposed brain tumor classification method is more robust than other traditional methods in terms of the evaluation metrics, sensitivity, specificity, and accuracy.

Performance Analysis of Deep Belief Neural Network for Brain Tumor Classification

“…The performance of the proposed DBN is evaluated in this section, and the performance results are compared with existing probabilistic neural network [3], Fuzzy Logic-Based Hybrid Kernel SVM [4] and KNN [7] schemes. The performance measurement is done in terms of precision, f-measurement, recall and accuracy.…”

“…The [4] fuzzy logic hybrid kernel has been created and applied for the automatic classification of four cancer types, including the meningioma, glioma, astrocytoma, and metastases called fuzzy logic hybrid kernel SVM, for the support of the Vector Machine.…”

Towards Better Segmentation of Abnormal Part in Multimodal Images Using Kernel Possibilistic C Means Particle Swarm Optimization With Morphological Reconstruction Filters

“…MRI brain tumors like Meningioma, Glioma, Astrocytoma, and Metastases are utilized to classify the tumor based on the attributes of the co-occurrence matrix and the histogram. Fuzzy logicbased hybrid kernel (Jayachandran & Kharmega Sundararaj, 2015) is used to test the classification for accuracy. T1-weighted MRI images are used to clustering for brain tumors with Principal Component Analysis (PCA) algorithm and compare the performance with PPCA, EM-PCA, GHA, APEX -they conclude that PPCA and EM-PPCA are efficient clustering algorithms.…”

Enhanced Decision Support Systems in Intensive Care Unit Based on Intuitionistic Fuzzy Sets

“…In the literature there are several studies in fuzzy logic (FL) for medical care which were grouped into six area: (i) neuromedical filed [2], (ii) blood glucose monitoring [3][4][5][6], 2 Advances in Fuzzy Systems (iii) neck and head cancer [7], (iv) breast cancer classification [2,8], (v) brain tumor extraction and classification [9], and (vi) emergency decision system [10].…”